Package org.cleartk.classifier.feature.extractor.simple

Examples of org.cleartk.classifier.feature.extractor.simple.SpannedTextExtractor


    // features created from the word text like character ngrams
    this.entityFeatureExtractors = Arrays.asList(
        new CoveredTextExtractor(),
        //new TypePathExtractor(IdentifiedAnnotation.class, "stem"),
        new ProliferatingExtractor(
            new SpannedTextExtractor(),
            new LowerCaseProliferator(),   
            new CapitalTypeProliferator(),
            new NumericTypeProliferator(),
            new CharacterNGramProliferator(fromRight, 0, 2),
            new CharacterNGramProliferator(fromRight, 0, 3)));

    // a list of feature extractors that require the token and the sentence
    this.contextFeatureExtractors = new ArrayList<ContextExtractor<IdentifiedAnnotation>>();
    this.contextFeatureExtractors.add(new ContextExtractor<IdentifiedAnnotation>(
        IdentifiedAnnotation.class,
        new CoveredTextExtractor(),
        //new TypePathExtractor(IdentifiedAnnotation.class, "stem"),
        new Preceding(2),
        new Following(2)));

    ContextExtractor<BaseToken> tokenContextExtractor1 = new ContextExtractor<BaseToken>(
        BaseToken.class,
        new SpannedTextExtractor(),
        new ContextExtractor.Ngram(new Covered()),
       
        new ContextExtractor.Ngram(new Preceding(1)),
        new ContextExtractor.Ngram(new Preceding(2)),
        //new ContextExtractor.Ngram(new Preceding(1, 2)),
View Full Code Here

TOP

Related Classes of org.cleartk.classifier.feature.extractor.simple.SpannedTextExtractor

Copyright © 2018 www.massapicom. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.